Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 927
    Prev
    Next
    INDEX
    Explanations

    information related to incidents, specifically focusing on details like injuries, arrests, and charges

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    121
    +0.11
    0.5%
    551
    +0.10
    0.4%
    104
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.11
    0.04
    114
    +0.10
    0.03
    79
    +0.09
    0.03
    Negative Logits
    issance
    -0.77
     smack
    -0.75
    bench
    -0.68
    oplan
    -0.67
     cram
    -0.63
    gemony
    -0.62
    pun
    -0.60
    ython
    -0.60
    tes
    -0.60
    zon
    -0.60
    POSITIVE LOGITS
     pending
    0.86
    irens
    0.81
    arnaev
    0.77
     TBD
    0.76
     coroner
    0.72
    Officials
    0.72
     forthcoming
    0.71
     confirmed
    0.69
    Authorities
    0.69
     nor
    0.68
    Activations Density 0.201%

    No Known Activations